This project will follow the 8 steps outlined below. Dataset was chosen to model the project from Chapter 2 and imported from the sklearn library.
The purpose of project is to predict the median value of prices of houses in the Boston area, using features provided from the dataset.
# importing necessary libraries and modules
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
%matplotlib inline
# importing data from sklearn
from sklearn.datasets import load_boston
boston_dataset = load_boston()
# viewing already assigned dataset keys
print(boston_dataset.keys())
dict_keys(['data', 'target', 'feature_names', 'DESCR', 'filename'])
#feature names
print(boston_dataset.feature_names)
['CRIM' 'ZN' 'INDUS' 'CHAS' 'NOX' 'RM' 'AGE' 'DIS' 'RAD' 'TAX' 'PTRATIO' 'B' 'LSTAT']
#detailed info on dataset and feature values
print(boston_dataset.DESCR)
.. _boston_dataset:
Boston house prices dataset
---------------------------
**Data Set Characteristics:**
:Number of Instances: 506
:Number of Attributes: 13 numeric/categorical predictive. Median Value (attribute 14) is usually the target.
:Attribute Information (in order):
- CRIM per capita crime rate by town
- ZN proportion of residential land zoned for lots over 25,000 sq.ft.
- INDUS proportion of non-retail business acres per town
- CHAS Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)
- NOX nitric oxides concentration (parts per 10 million)
- RM average number of rooms per dwelling
- AGE proportion of owner-occupied units built prior to 1940
- DIS weighted distances to five Boston employment centres
- RAD index of accessibility to radial highways
- TAX full-value property-tax rate per $10,000
- PTRATIO pupil-teacher ratio by town
- B 1000(Bk - 0.63)^2 where Bk is the proportion of black people by town
- LSTAT % lower status of the population
- MEDV Median value of owner-occupied homes in $1000's
:Missing Attribute Values: None
:Creator: Harrison, D. and Rubinfeld, D.L.
This is a copy of UCI ML housing dataset.
https://archive.ics.uci.edu/ml/machine-learning-databases/housing/
This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.
The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic
prices and the demand for clean air', J. Environ. Economics & Management,
vol.5, 81-102, 1978. Used in Belsley, Kuh & Welsch, 'Regression diagnostics
...', Wiley, 1980. N.B. Various transformations are used in the table on
pages 244-261 of the latter.
The Boston house-price data has been used in many machine learning papers that address regression
problems.
.. topic:: References
- Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.
- Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.
#changing dataset into pandas df for rest of project
#adding target variable to dataset
boston = pd.DataFrame(data=boston_dataset.data, columns=boston_dataset.feature_names)
boston["MEDV"] = boston_dataset.target
boston.head(5)
| CRIM | ZN | INDUS | CHAS | NOX | RM | AGE | DIS | RAD | TAX | PTRATIO | B | LSTAT | MEDV | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.00632 | 18.0 | 2.31 | 0.0 | 0.538 | 6.575 | 65.2 | 4.0900 | 1.0 | 296.0 | 15.3 | 396.90 | 4.98 | 24.0 |
| 1 | 0.02731 | 0.0 | 7.07 | 0.0 | 0.469 | 6.421 | 78.9 | 4.9671 | 2.0 | 242.0 | 17.8 | 396.90 | 9.14 | 21.6 |
| 2 | 0.02729 | 0.0 | 7.07 | 0.0 | 0.469 | 7.185 | 61.1 | 4.9671 | 2.0 | 242.0 | 17.8 | 392.83 | 4.03 | 34.7 |
| 3 | 0.03237 | 0.0 | 2.18 | 0.0 | 0.458 | 6.998 | 45.8 | 6.0622 | 3.0 | 222.0 | 18.7 | 394.63 | 2.94 | 33.4 |
| 4 | 0.06905 | 0.0 | 2.18 | 0.0 | 0.458 | 7.147 | 54.2 | 6.0622 | 3.0 | 222.0 | 18.7 | 396.90 | 5.33 | 36.2 |
#double checking for null values
boston.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 506 entries, 0 to 505 Data columns (total 14 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 CRIM 506 non-null float64 1 ZN 506 non-null float64 2 INDUS 506 non-null float64 3 CHAS 506 non-null float64 4 NOX 506 non-null float64 5 RM 506 non-null float64 6 AGE 506 non-null float64 7 DIS 506 non-null float64 8 RAD 506 non-null float64 9 TAX 506 non-null float64 10 PTRATIO 506 non-null float64 11 B 506 non-null float64 12 LSTAT 506 non-null float64 13 MEDV 506 non-null float64 dtypes: float64(14) memory usage: 55.5 KB
#plotting historgram for each numerical attribute
import seaborn as sns
sns.pairplot(boston)
<seaborn.axisgrid.PairGrid at 0x7f9cc4ca3460>
#plotting distribution of target variable (median value of homes)
sns.set(rc={'figure.figsize':(11.7,8.27)})
sns.distplot(boston['MEDV'], bins=30)
plt.xlabel("House prices in $1000")
plt.show()
/Users/ellabrucker/opt/anaconda3/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
# prices seem to be normally distributed. Maybe a couple outliers
#dropping predicted value
boston_pred = boston.drop(['MEDV'], axis = 1)
boston_pred
| CRIM | ZN | INDUS | CHAS | NOX | RM | AGE | DIS | RAD | TAX | PTRATIO | B | LSTAT | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.00632 | 18.0 | 2.31 | 0.0 | 0.538 | 6.575 | 65.2 | 4.0900 | 1.0 | 296.0 | 15.3 | 396.90 | 4.98 |
| 1 | 0.02731 | 0.0 | 7.07 | 0.0 | 0.469 | 6.421 | 78.9 | 4.9671 | 2.0 | 242.0 | 17.8 | 396.90 | 9.14 |
| 2 | 0.02729 | 0.0 | 7.07 | 0.0 | 0.469 | 7.185 | 61.1 | 4.9671 | 2.0 | 242.0 | 17.8 | 392.83 | 4.03 |
| 3 | 0.03237 | 0.0 | 2.18 | 0.0 | 0.458 | 6.998 | 45.8 | 6.0622 | 3.0 | 222.0 | 18.7 | 394.63 | 2.94 |
| 4 | 0.06905 | 0.0 | 2.18 | 0.0 | 0.458 | 7.147 | 54.2 | 6.0622 | 3.0 | 222.0 | 18.7 | 396.90 | 5.33 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 501 | 0.06263 | 0.0 | 11.93 | 0.0 | 0.573 | 6.593 | 69.1 | 2.4786 | 1.0 | 273.0 | 21.0 | 391.99 | 9.67 |
| 502 | 0.04527 | 0.0 | 11.93 | 0.0 | 0.573 | 6.120 | 76.7 | 2.2875 | 1.0 | 273.0 | 21.0 | 396.90 | 9.08 |
| 503 | 0.06076 | 0.0 | 11.93 | 0.0 | 0.573 | 6.976 | 91.0 | 2.1675 | 1.0 | 273.0 | 21.0 | 396.90 | 5.64 |
| 504 | 0.10959 | 0.0 | 11.93 | 0.0 | 0.573 | 6.794 | 89.3 | 2.3889 | 1.0 | 273.0 | 21.0 | 393.45 | 6.48 |
| 505 | 0.04741 | 0.0 | 11.93 | 0.0 | 0.573 | 6.030 | 80.8 | 2.5050 | 1.0 | 273.0 | 21.0 | 396.90 | 7.88 |
506 rows × 13 columns
def split_train_test(boston_pred, test_ratio):
shuffled_indices = np.random.permutation(len(boston_pred))
test_set_size = int(len(boston) * test_ratio)
test_indices = shuffled_indices[:test_set_size]
train_indices = shuffled_indices[test_set_size:]
return boston_pred.iloc[train_indices], boston_pred.iloc[test_indices]
train_set, test_set = split_train_test(boston_pred, 0.1)
print(len(train_set), "train +", len(test_set), "test")
456 train + 50 test
# keeping test set consistent by computing hash of each instance's identifier
import hashlib
def test_set_check(identifier, test_ratio, hash):
return hash(np.int64(identifier)).digest()[-1] < 256 * test_ratio
def split_train_test_by_id(boston_pred, test_ratio, id_column, hash=hashlib.md5):
ids = boston_pred[id_column]
in_test_set = ids.apply(lambda id_: test_set_check(id_, test_ratio, hash))
return boston_pred.loc[~in_test_set], boston_pred.loc[in_test_set]
# X = feature matrix
X = boston[['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX',
'PTRATIO', 'B', 'LSTAT']]
#y = target vector
Y = boston['MEDV']
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.1, random_state=50)
print(X_train.shape)
print(X_test.shape)
print(Y_train.shape)
print(Y_test.shape)
(455, 13) (51, 13) (455,) (51,)
#EDA with pandas profiling
import pandas_profiling
boston.profile_report()